Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to importance or essentiality

    oai_token-act-pair · gpt-3.5-turbo

    references to essential or crucial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AUT
    -0.79
    ©¶æ
    -0.73
    annis
    -0.72
    renheit
    -0.69
    sein
    -0.69
    Ń·
    -0.68
    hang
    -0.67
    ften
    -0.66
    ATT
    -0.66
     Sett
    -0.65
    POSITIVE LOGITS
     organs
    0.90
     vital
    0.90
     destro
    0.85
    ogical
    0.80
    istically
    0.80
    rament
    0.79
    itational
    0.77
    arial
    0.75
    emic
    0.74
    istical
    0.74
    Act Density 0.006%

    No Known Activations